Make tcp worker multithreaded, too

This shamelessly steals the model established in the UDP workers, i.e.
if the kernel is able to bind multiple listening sockets to the same
endpoint, we will share them across threads. If it can't, all threads
will accept on the same socket.

The fast path handles most of the connections, only the rare case of
no data yet on the socket is offloaded to the slow path (which used to
be the mainloop) for completion. This scales nicely, as the higher the
load is, the higher chances are that an accept happens only after the
network roundtrip to the peer completes, leading to more connections
that already have data waiting for us.

We also consolidate the workstruct init and deinit code, preparation
for later unifying all thread state structs for all protocols (mca,
udc and tcp).

The config file gains a per tcp connection worker count and some docs
explaining what this knob buys and costs, nudging the user to either
keep it 0 or dial it up to at least 2.

1 files changed, 6 insertions, 0 deletions

diff --git a/ot_tcp.h b/ot_tcp.h
index b0a93f4..96b6ec1 100644
--- a/ot_tcp.h
+++ b/ot_tcp.h
@@ -19,4 +19,10 @@ void tcp_accept(const int64_t serversocket, struct ot_workstruct *ws);
 void tcp_read(const int64_t sock, struct ot_workstruct *ws);
 void tcp_write(const int64_t sock);
 
+/* One thread accepting on one socket. Called once per worker. */
+void tcp_worker_install(int64_t sock);
+
+/* Stop every worker installed above and wait for it to be gone */
+void tcp_workers_deinit(void);
+
 #endif